两电机调速系统的神经网络逆在线调整控制

针对MIMO非线性强耦合的两电机变频调速系统,在基于神经网络逆系统离线训练的基础上提出了在线调整的策略,通过静态神经网络加积分器来构造两电机变频调速系统的逆模型,在实际运行中不断地修正神经网络权值,更精确地逼近其逆系统,实现MIMO系统的线性化与解耦.仿真和实验结果表明,系统具有优良的动静态解耦性能和较强的抗负载扰动的能力.

On-line Adjustment Control of Two Motor Variable Speed-regulating System based on Neural Network Inverse

Two motor variable frequency speed-regulating system is a MIMO,nonlinear and high coupling control system.A strategy of controling on-line based on artificial neural network(ANN)inverse system is proposed,by which the MIMO non-linear system can be transformed into a number of SISO linear subsystems.A static ANN and a integrator are used to con-struct the ANN inverse of the two motor variable frequency speed-regulating system,in which the connection value can be amended on-line in order to approach the inver...